Issue release date: 12.11.2024
2University Hospital of Zurich, Department of Neuroradiology, Zurich, Switzerland
3Weill Cornell Medical College, NewYork-Presbyterian Hospital, Department of Neurosurgery, New York, USA
4Democritus University of Thrace Medical School, 1st University Surgery Department, Alexandroupolis, Greece
5General Hospital “G. Papanikolaou”, Department of Neurosurgery, Thessaloniki, Greece DOI : 10.5137/1019-5149.JTN.8492-13.0 AIM: To identify key determinants of lumbar disc herniation (LDH) patients’ satisfaction and to evaluate the efficiency of an artificial neural network (ANN) model to prognosticate satisfaction derived from the hospital stay in this specific patient group.
MATERIAL and METHODS: A single item question was used to assess patient satisfaction. Principal component analysis evaluated several aspects of care (15 items). An ANN encompassed all variables and its prediction ability was tested. The ANN performance was correlated to a binary logistic regression (BLR) model.
RESULTS: Higher levels of satisfaction were reported by females, older patients, Greeks, and patients with elementary education staying in not rural areas. A history of a single previous hospitalisation was correlated with more satisfaction. The accuracy of ANN was 96% for satisfaction prediction outperforming the BLR model.
CONCLUSION: Satisfactory health services are influenced by sex, age, nationality, and number of prior admissions. The selfperceived health state plays also a crucial role. The current study is the first one reporting on the capability of an ANN to accurately predict the satisfaction levels of LDH patients.
Keywords : Artificial neural network, Health services research, Lumbar disc herniation, Patient, Prediction, Regression, Satisfaction